Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    fontsize, 'rc', 'exponential'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ów
    0.56
     G
    0.48
     путь
    0.48
    剛剛
    0.48
     LOCCTR
    0.48
    𝓸
    0.48
     设备
    0.47
    espół
    0.47
     звук
    0.46
     話
    0.46
    POSITIVE LOGITS
    ppin
    0.52
    Exponential
    0.50
    ppet
    0.46
     प्रधाना
    0.44
    ppen
    0.44
    pp
    0.44
    氳
    0.44
    غي
    0.43
     exponential
    0.43
    exponential
    0.42
    Act Density 0.000%

    No Known Activations